Method for generating detailed visualization of machine learning model behavior
AssigneeNXP B.V.
InventorPeter Doliwa
Life of this patent
Estimating the term…
Abstract
A method is provided for generating a visualization for explaining a behavior of a machine learning (ML) model, the method includes inputting an image into a machine learning (ML) model for an inference operation. A first heatmap is generated for the image using a first visualization method. An area of highest attention is selected on the first heatmap based a predetermined threshold. The selected area is cropped from the image. The cropped selected area is upscaled. A second heatmap is generated for the cropped and upscaled selected area of the image. A final visualization is presented for analysis. In another embodiment, a computer program comprising instructions for executing the method is provided.
Claims18
A method for generating a visualization for explaining a behavior of a machine learning (ML) model, the method comprising:
- inputting an image having an input pixel resolution into a ML model for an inference operation, wherein the input pixel resolution corresponds to the input resolution of the ML model;
- generating a first heatmap for the image using a first visualization method;
- selecting an area of highest attention on the first heatmap using a predetermined threshold;
- mapping the selected area of highest attention of the first heatmap to the image;
- cropping the selected area of highest attention indicated on the first heatmap from the image;
- upscaling the cropped selected area from the image to generate a cropped and upscaled selected area of the image using all of the input pixel resolution for the cropped and upscaled selected area;
- generating a second heatmap for the cropped and upscaled selected area of the image;
- and
- presenting a final visualization for analysis using the second heatmap.
A computer program comprising instructions executable by a processor, for executing a method for generating a visualization for explaining a behavior of a machine learning (ML) model, the executable instructions comprising:
- instructions for inputting an image having an input pixel resolution into a ML model for an inference operation, wherein the input pixel resolution corresponds to the input resolution of the ML model;
- instructions for generating a first heatmap for the image using a first visualization method;
- instructions for selecting an area of highest attention on the first heatmap using a predetermined threshold;
- instructions for mapping the selected area of highest attention of the first heatmap to the image;
- instructions for cropping the selected area of highest attention indicated on the first heatmap from the image;
- instructions for upscaling the cropped selected area from the image to generate a cropped and upscaled selected area of the image using all of the input pixel resolution for the cropped and upscaled selected area;
- instructions for generating a second heatmap for the cropped and upscaled selected area of the image;
- and
- instructions for presenting a final visualization for analysis using the second heatmap.
Dependencies are inferred from the claim text.